{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T17:12:04Z","timestamp":1785604324559,"version":"3.56.0"},"reference-count":109,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3545032","type":"journal-article","created":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T18:41:32Z","timestamp":1740422492000},"page":"41822-41838","source":"Crossref","is-referenced-by-count":23,"title":["Transformer-Based Sensor Fusion for Autonomous Vehicles: A Comprehensive Review"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7493-3564","authenticated-orcid":false,"given":"Ahmed","family":"Abdulmaksoud","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, Centre for Mechatronics and Hybrid Technologies (CMHT), McMaster University, Hamilton, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5805-2132","authenticated-orcid":false,"given":"Ryan","family":"Ahmed","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Centre for Mechatronics and Hybrid Technologies (CMHT), McMaster University, Hamilton, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21977"},{"key":"ref2","volume-title":"Autonomous Vehicles: Moving Forward-perspectives From Industry Leaders","year":"2021"},{"issue":"15","key":"ref3","doi-asserted-by":"crossref","first-page":"4220","DOI":"10.3390\/s20154220","article-title":"Deep learning sensor fusion for autonomous vehicle perception and localization: A review","volume":"20","author":"Fayyad","year":"2020","journal-title":"Sensors"},{"key":"ref4","volume-title":"Automatic Emergency Braking (AEB) System Performance Testing","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2136\/1\/012036"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00355"},{"issue":"6","key":"ref7","doi-asserted-by":"crossref","first-page":"2140","DOI":"10.3390\/s21062140","article-title":"Sensor and sensor fusion technology in autonomous vehicles: A review","volume":"21","author":"Yeong","year":"2021","journal-title":"Sensors"},{"key":"ref8","volume-title":"Buy Intel Realsense Depth Camera D455","year":"2023"},{"key":"ref9","volume-title":"LiDAR Price: How Much Does LiDAR Cost?","year":"2023"},{"key":"ref10","volume-title":"ARS-408 Radar Sensor","year":"2023"},{"issue":"1","key":"ref11","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.inffus.2011.08.001","article-title":"Multisensor data fusion: A review of the state-of-the-art","volume":"14","author":"Khaleghi","year":"2013","journal-title":"Inf. Fusion"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/s91007771"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SDF.2019.8916629"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10040424"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/s22186791"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1117\/12.2673838"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref19","article-title":"RecurrentGemma: Moving past transformers for efficient open language models","author":"Botev","year":"2024","journal-title":"arXiv:2404.07839"},{"key":"ref20","article-title":"ITransformer: Inverted transformers are effective for time series forecasting","author":"Liu","year":"2023","journal-title":"arXiv:2310.06625"},{"key":"ref21","article-title":"Transformers in speech processing: A survey","author":"Latif","year":"2023","journal-title":"arXiv:2303.11607"},{"key":"ref22","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2022.3186505"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.36227\/techrxiv.20443107.v2"},{"key":"ref25","article-title":"Multi-modal sensor fusion-based deep neural network for end-to-end autonomous driving with scene understanding","author":"Huang","year":"2020","journal-title":"arXiv:2005.09202"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2972974"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"271","DOI":"10.26855\/acc.2023.10.002","article-title":"Lane tracking in self-driving cars: Leveraging TensorFlow for deep learning in image processing across localization, and sensor fusion","volume":"4","author":"Abdullahi","year":"2023","journal-title":"Advances in Computer and Communication"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2962554"},{"key":"ref29","article-title":"Challenges and opportunities of using transformer-based multi-task learning in NLP through ML lifecycle: A survey","author":"Torbarina","year":"2023","journal-title":"arXiv:2308.08234"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3317372"},{"key":"ref31","article-title":"Multi-modal sensor fusion for auto driving perception: A survey","author":"Huang","year":"2022","journal-title":"arXiv:2202.02703"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRAS49812.2020.9135065"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00033"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00752"},{"key":"ref35","first-page":"10421","article-title":"BEVFusion: A simple and robust LiDAR-camera fusion framework","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liang"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref37","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2017","journal-title":"arXiv:1709.01507"},{"key":"ref38","article-title":"Multi-view 3D object detection network for autonomous driving","author":"Chen","year":"2016","journal-title":"arXiv:1611.07759"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200245"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01515"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341791"},{"key":"ref42","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","author":"Katharopoulos","year":"2020","journal-title":"arXiv:2006.16236"},{"key":"ref43","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref44","article-title":"NuScenes: A multimodal dataset for autonomous driving","author":"Caesar","year":"2019","journal-title":"arXiv:1903.11027"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00159"},{"key":"ref47","article-title":"The ApolloScape open dataset for autonomous driving and its application","author":"Huang","year":"2018","journal-title":"arXiv:1803.06184"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref49","article-title":"Scalability in perception for autonomous driving: Waymo open dataset","author":"Sun","year":"2019","journal-title":"arXiv:1912.04838"},{"key":"ref50","article-title":"K-radar: 4D radar object detection for autonomous driving in various weather conditions","author":"Paek","year":"2022","journal-title":"arXiv:2206.08171"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3419689"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11554-022-01202-6"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3312382"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00293"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1117\/12.2663424"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3145192"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897588"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3390\/rs15133396"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00019"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01666"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564951"},{"key":"ref64","article-title":"DeepInteraction: 3D object detection via modality interaction","author":"Yang","year":"2022","journal-title":"arXiv:2208.11112"},{"key":"ref65","article-title":"Unifying voxel-based representation with transformer for 3D object detection","author":"Li","year":"2022","journal-title":"arXiv:2206.00630"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01675"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096129"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/iros55552.2023.10341793"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.4271\/2023-01-7040"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25198"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10161329"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/jsen.2024.3357775"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3507538"},{"key":"ref74","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"9","key":"ref76","doi-asserted-by":"crossref","first-page":"7260","DOI":"10.3390\/su15097260","article-title":"The effect of rainfall and illumination on automotive sensors detection performance","volume":"15","author":"Li","year":"2023","journal-title":"Sustainability"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956149"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.23919\/ICIF.2018.8455757"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.23919\/FUSION43075.2019.9011192"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3387113"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/s00202-022-01590-9"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3385439"},{"issue":"1","key":"ref83","doi-asserted-by":"crossref","first-page":"220","DOI":"10.3390\/electronics13010220","article-title":"Multi-modal contrastive learning for LiDAR point cloud rail-obstacle detection in complex weather","volume":"13","author":"Wen","year":"2024","journal-title":"Electronics"},{"issue":"2","key":"ref84","first-page":"1344","article-title":"Fusion-vital: Video-RF fusion transformer for advanced remote physiological measurement","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"38","author":"Choi"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00058"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2993703"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO55434.2022.10011808"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6409"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.3390\/s23156783"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.3390\/rs12234007"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1117\/12.3026289"},{"key":"ref92","article-title":"FrameQuant: Flexible low-bit quantization for transformers","author":"Adepu","year":"2024","journal-title":"arXiv:2403.06082"},{"key":"ref93","article-title":"State space model for new-generation network alternative to transformers: A survey","author":"Wang","year":"2024","journal-title":"arXiv:2404.09516"},{"key":"ref94","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref95","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024","journal-title":"arXiv:2401.09417"},{"key":"ref96","article-title":"XLSTM: Extended long short-term memory","author":"Beck","year":"2024","journal-title":"arXiv:2405.04517"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1002\/int.22818"},{"key":"ref98","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101890","article-title":"FL-FD: Federated learning-based fall detection with multimodal data fusion","volume":"99","author":"Qi","year":"2023","journal-title":"Inf. Fusion"},{"key":"ref99","article-title":"Federated learning for connected and automated vehicles: A survey of existing approaches and challenges","author":"Chellapandi","year":"2023","journal-title":"arXiv:2308.10407"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.4236\/jcc.2021.95007"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP52444.2021.9651941"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3145972"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/UCET51115.2020.9205411"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1515"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1049\/cmu2.12314"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.3390\/a17110526"},{"issue":"4","key":"ref107","first-page":"957","article-title":"Key problems and progress of vision transformers: The state of the art and prospects","volume":"48","author":"Tian","year":"2022","journal-title":"Zidonghua Xuebao\/Acta Autom. Sinica"},{"key":"ref108","article-title":"On the performance and memory footprint of distributed training: An empirical study on transformers","author":"Lu","year":"2024","journal-title":"arXiv:2407.02081"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3084396"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10901945.pdf?arnumber=10901945","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T17:42:16Z","timestamp":1741714936000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10901945\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":109,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3545032","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}